Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-file-manager show directory tree of current folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives AI agents file system access: read, write, search, hash, directory trees — 12 tools, zero dependencies, pure Python stdlib.
12 MCP Tools: read_file, read_file_lines, write_file, append_file, delete_file, copy_file, move_file, list_directory, search_files, file_info, file_hash, directory_tree
Zero dependencies — pure Python stdlib (os, shutil, hashlib, fnmatch, pathlib)
Content search — grep-like search inside files (20+ file extensions)
File hashing — MD5, SHA-1, SHA-256, SHA-512
Directory trees — recursive tree generation with depth control
STDIO JSON-RPC mode — drop-in for Claude Desktop, Hermes, or any MCP client
Related MCP server: enhanced-filesystem-mcp
python -m src.server --stdio # STDIO mode
python -m src.server --manifest # Print manifestfrom src.server import MCPFileManagerServer
import json
server = MCPFileManagerServer()
# Write a file
server.handle_tool_call("write_file", {"path": "/tmp/test.txt", "content": "Hello!"})
# Read it back
result = json.loads(server.handle_tool_call("read_file", {"path": "/tmp/test.txt"}))
print(result["content"]) # "Hello!"
# Search for files
result = server.handle_tool_call("search_files", {"path": ".", "pattern": "*.py", "target": "files"})
# Search inside files (grep)
result = server.handle_tool_call("search_files", {"path": ".", "pattern": "TODO", "target": "content"})
# Get file hash
result = server.handle_tool_call("file_hash", {"path": "/tmp/test.txt", "algorithm": "sha256"})
# Directory tree
result = server.handle_tool_call("directory_tree", {"path": ".", "max_depth": 3})Tool | Description | Required Params |
| Read file content |
|
| Read specific lines |
|
| Write file (creates dirs) |
|
| Append to file |
|
| Delete file or dir |
|
| Copy file or dir |
|
| Move/rename |
|
| List dir contents | — |
| Find by name or grep |
|
| File metadata |
|
| File hash (md5/sha256) |
|
| Directory tree | — |
python -m pytest tests/ -v # 36 tests, all passingMIT
aaameobius-crypto — github.com/aaameobius-crypto
Freelance portfolio: https://ameobius-space.github.io/kwork-portfolio/
This server cannot be deployed
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.
